TW202100990A - Appearance inspection management system, device, method and program including a photographing component, an inspection component, a defect candidate extraction component, a display component and a visual inspection auxiliary part - Google Patents

Abstract

The present invention provides a technique for making an efficient judgment of a visual inspection on an appearance inspection of an inspected object, moreover, preventing the visual inspection from fluctuations of inspection standards due to performing a visual inspection. An appearance inspection management system includes: a photographing component, which photographs the inspected object; an inspection component, which inspects the inspected object based on images photographed by the photographing component; a defect candidate extraction component, which extracts defect candidate images having a feature value within a predetermined difference range with respect to a predetermined threshold from the images photographed by the photographic component; a display component; and a visual inspection auxiliary part. An image list display and a defect determination line are displayed on the display component. The image list display includes one or more defect candidate images arranged according to their feature values. The defect determination line indicates the threshold value, and any of the defect candidate images in the image list display are determined to be a defect or not based on the threshold value.

Description

Appearance inspection management system, appearance inspection management device, appearance inspection management method and program

The present invention relates to an appearance inspection, which is based on an image of the inspection object taken by irradiating the inspection object with illumination light to inspect the inspection object. Specifically, the present invention relates to an appearance inspection management system , Appearance inspection management device, appearance inspection management method and program.

Conventionally, there has been known an appearance inspection apparatus that performs inspection of the inspection object based on an image of the inspection object taken by irradiating the inspection object with illumination light.

For example, Patent Document 1 discloses an inspection device that analyzes an image obtained by irradiating visible light or ultraviolet light to a sheet and photographing the transmitted light or reflected light with a camera. Detection of abnormalities in the sheet (foreign matter mixing, stains, wrinkles, etc., also referred to as defects hereinafter).

In this type of visual inspection device, the value of the feature amount extracted from the captured image is compared with a preset threshold value to automatically determine the presence or absence or type of a defect. However, the defect judgment often results in strict results in the sense of preventing omissions. Conventionally, a secondary visual inspection has been performed on an image of a part temporarily detected as a defect. Moreover, the inspection threshold in the visual inspection device is generally reset based on the secondary inspection by the visual inspection. [Prior Art Literature] [Patent Literature]

Patent Document 1: Japanese Patent Laid-Open No. 2015-172519

[The problem to be solved by the invention]

In addition, when the secondary inspection by visual inspection is performed as described above, an image with a feature value close to the threshold, which is relatively difficult to determine a defect, is mixed with an image with a feature value that is clearly deviated from the threshold, which can be clearly identified as a defect. The totality of existence becomes the object.

Therefore, there is a problem in that the time required for visual inspection of an image whose necessity of visual inspection is originally low is wasted. In addition, there is a problem in that every time such a large number of images are visually inspected, the judgment made by the inspector fluctuates (that is, the inspection standard fluctuates). In addition, there is a problem in that if the inspection threshold of the inspection device is set (changed) based on such fluctuating defect determinations, the inspection standard cannot always be determined once, and the inspection accuracy cannot be improved.

The present invention has been completed in view of the actual situation as described above, and its object is to provide a technique to make the judgment of visual inspection in the appearance inspection of an inspection object more efficient and prevent fluctuations in inspection criteria due to visual inspection. [Means to solve the problem]

In order to achieve the object, the present invention adopts the following structure.

The appearance inspection management system of the present invention includes: a photographing component, which photographs an inspection object; and an inspection component, which compares the feature amount obtained from the image of the inspection object photographed by the photographing component with a predetermined threshold, thereby making a determination, To detect defects in the inspected object; defect candidate extraction means for extracting, from the inspected object image, a defect candidate image having a feature value within a predetermined difference range with respect to the predetermined threshold ; Display part; and a visual inspection auxiliary part for displaying a list of images and a defect determination line on the display part, and the list of images is based on the value of the feature value of each image to display more than one The defect candidate images are arranged, the defect determination line indicates the threshold, and the defect candidate images in the image list display are classified according to whether they are judged to be defects according to the threshold.

In addition, as the feature quantity referred to here, various types of feature quantity such as brightness (depth) distribution of the image, brightness peak level, area, width, length, longest and shortest Feret diameter ratio, and roundness can be applied. In addition, in the following, the image of the inspection object photographed in the appearance inspection member is also referred to as an inspection object image. In addition, it is also possible to adopt a configuration in which the inspection unit also serves as the defect candidate extraction unit, that is, a portion having a feature value within a predetermined difference range from the predetermined threshold value is detected as a defect, The image captured at the defect site is extracted as a defect candidate image.

According to the visual inspection management system having such a structure, a user who performs visual inspection as a secondary inspection of visual inspection can compare multiple defect candidate images with a defect judgment line that represents an objective index, that is, a threshold value, thereby performing visual inspection. It can prevent fluctuations in inspection standards.

Furthermore, a plurality of the thresholds may be provided, and the visual inspection auxiliary component displays the defect determination line corresponding to the number of the thresholds. Furthermore, the inspection component may acquire a variety of feature quantities from the image of the object to be inspected, and detect the defect of the object to be inspected based on a threshold value corresponding to each feature quantity. In this way, defects can be reduced based on multiple viewpoints, and the content of defects can be segmented.

Furthermore, the image list display may be formed by arranging one or more of the defect candidate images according to the value of the feature amount of each image corresponding to each type of feature amount. With such a configuration, when a plurality of feature amounts are used, the visibility of the list display can be improved.

Furthermore, it may further include: a defect type classification means, which classifies the type of the defect when a defect is detected from the inspection object. Furthermore, the visual inspection auxiliary component may correspond to each type of defect classified by the defect type classification component, and the number of the defects may be displayed on the display component. With this structure, the types of defects can be classified and the image data can be managed, and the inspection can be managed based on more detailed information.

Furthermore, the visual inspection management system may further include: an input unit; and an inspection result correction unit that receives at least one of the defect determination line and the defect candidate images in the image list display via the input unit A relative movement operation. By having such a structure, it is possible to correct the determination result of a specific image through a dialogue operation.

Furthermore, the inspection result correction part may be used by the operation to display the attention display of the defect candidate image that has moved to the opposite side of the defect determination line compared to before the operation, and is displayed on The display part. With this structure, when the inspection result is corrected, the corrected condition and its content can be easily recognized.

Furthermore, the inspection result correction means may accept an operation of relatively moving the defect determination line and at least one of the defect candidate images in the image list display, thereby setting and/or changing the predetermined threshold value . By having such a structure, it is possible to change the threshold value through dialogue-based operation.

Furthermore, the visual inspection auxiliary component may display the feature quantity distribution map and the image list display simultaneously or switchably on the display component in the coordinate system defined by predetermined feature quantities, The feature quantity distribution map is arranged with values of feature quantities obtained from one or more of the inspection object images as coordinates of the coordinate system. Moreover, the inspection management system may further include: a threshold setting component that sets and/or changes the predetermined threshold, and displays a threshold display line indicating the predetermined threshold on the characteristic quantity distribution graph. When the threshold value setting means changes the predetermined threshold value, the change of the threshold value is reflected in the display of the threshold value display line.

In addition, the threshold value setting means may also have a structure that also serves as the inspection result correction means. With such a configuration, the distribution of the feature amount in the image of the inspection object and the relationship with the inspection threshold can be confirmed at a glance. Furthermore, it is possible to study the difference area of the extracted defect candidate image while comparing the distribution of the threshold value display line and the feature amount.

Furthermore, the inspection object in the visual inspection management system may be a sheet-like article. Furthermore, the visual inspection management system may include at least an inspection management device having the visual inspection auxiliary component as a constituent element.

Furthermore, the visual inspection management method of the present invention manages the visual inspection of the inspected object. The visual inspection management method includes: a photographing step, photographing the inspected object; a defect candidate extraction step, extracting defect candidate images, the defect The candidate image is an image in which the feature amount obtained from the image of the inspection object taken in the photographing step converges within a predetermined difference range with respect to a predetermined threshold; and the visual inspection auxiliary step makes the image The list display and the defect determination line are displayed on the same screen, and the image list display is based on the value of the feature amount of each image to group one or more of the defect candidate maps extracted in the defect candidate extraction step The defect determination line indicates the threshold value, and the defect candidate images in the image list display are classified according to whether they are determined to be defects or not based on the relationship with the threshold value.

Furthermore, the present invention can also be understood as a storage medium that stores a program for causing an information processing device to execute the method, and is a computer-readable storage medium on which such a program is not temporarily recorded.

Moreover, each of the aforementioned structures and processes can be combined with each other to form the present invention as long as no technical contradiction occurs. [Effects of the invention]

According to the present invention, it is possible to provide a technique for making the judgment of the visual inspection in the appearance inspection of the inspection object more efficient, and preventing the fluctuation of the inspection standard due to the visual inspection.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

＜Application example＞ (system structure) The present invention can be applied to, for example, the appearance inspection management system 9 shown in FIG. 1. FIG. 1 is a schematic diagram showing a schematic configuration of an appearance inspection management system 9 of this application example. The appearance inspection management system 9 includes an appearance inspection device 91 and an inspection management device 92.

The appearance inspection device 91 is a device that takes an image of an inspection object (not shown) and inspects the inspection object for defects based on the image. As shown in FIG. 1, as a main structure, it has The light source 911 of the lighting unit, the camera 912 as the imaging unit, and the control terminal 913. In addition, the control terminal 913 corresponds to the inspection means and defect candidate extraction means in the present invention.

The light source 911 is configured to be able to irradiate the inspection object and the calibration standard plate 95 with illumination light. The camera 912 is a photographing means that photographs an inspection object in a state irradiated with illumination light, and outputs a digital image. In addition, below, the image of the inspection object imaged by the imaging means is also referred to as an inspection object image. The camera 912 includes, for example, an optical system and an image sensor.

The control terminal 913 has functions such as the control of the light source 911 and the camera 912, and the processing of the image imported from the camera 912, and is equivalent to the inspection means in the present invention. The control terminal 913 can include a computer, which includes a central processing unit (CPU), a random access memory (Random Access Memory, RAM), and a non-volatile memory device (such as a hard disk drive). (Hard disk drive, flash memory, etc.), input devices (such as keyboard, mouse, touch panel, etc.).

When the appearance inspection of the inspection object is performed in the appearance inspection apparatus 91 having the above-mentioned structure, the camera 912 captures an image of the inspection object in a state where the illumination light is irradiated from the light source 911, and the control terminal 913 responds The captured image is subjected to image processing, and by comparing the obtained feature value with a preset inspection threshold value, a part with a feature value deviating from the threshold value is determined as a defect.

Next, the functions of the control terminal 913 will be described. The control terminal 913 includes an image acquisition unit 9131, a feature quantity calculation unit 9132, a defect determination unit 9133, and a defect candidate image acquisition unit 9134 as functional modules related to appearance inspection.

The image acquisition unit 9131 is a function of importing an image from the camera 912, and for example, acquires an inspection object image of an inspection object in a state irradiated with illumination light. The feature amount calculation unit 9132 is a function of calculating the feature amount used for the appearance inspection based on the inspection object image. In addition, the feature quantity is not limited to one. For example, various feature quantities such as the brightness (depth) distribution of the image, the brightness peak level, area, width, length, longest and shortest Feret diameter ratio, and roundness can be calculated.

The defect determination unit 9133 compares the feature amount calculated by the feature amount calculation unit 9132 with a preset threshold value, and determines a portion having a feature amount deviating from the threshold value as a defect. In addition, the defect candidate extraction unit 9134 is a function of extracting, from the inspection object image, a defect candidate image having a characteristic value within a certain range of a threshold value used for defect determination. .

The inspection management device 92 has a function of displaying an image of a part determined as a defect by the visual inspection device 91 for secondary determination, a function of setting the types of feature quantities used in inspection in the visual inspection device 91 and their threshold values, and the like. The inspection management device 92 can include a computer including a CPU, a RAM, a nonvolatile memory device, an input device, and a display component (for example, a liquid crystal display, etc.) 93.

The inspection management device 92 has a defect candidate image acquisition unit 921 and a visual inspection support unit 922 as functional modules. The defect candidate image acquisition unit 921 is a function of acquiring the defect candidate image extracted by the defect candidate extraction unit 9134 from the appearance inspection device 91. The visual inspection support unit 922 is a function of displaying a list of images displayed in a list and a defect determination line on the display unit 93. The list of images displayed in the list displays defect candidates based on the value of the feature value of each image. The images are arranged, the defect determination line indicates the threshold value, and the defect candidate images displayed in the list are divided according to whether or not it is determined to be a defect based on the threshold value.

FIG. 2 shows an example of a screen displayed on the display part 93 by the visual inspection support unit 922. 2 shows a state in which defect candidate images whose feature values are close to the threshold value are arranged in order from the left in the order of feature values when the areas of parts with different shades are used as feature quantities. The dotted line in FIG. 2 is a defect determination line indicating a threshold value, and the part indicated by the image located on the left side of the line is detected as a defect in the visual inspection device 91. That is, the defect determination line divides the three images on the left and the two images on the right according to whether it is determined to be a defect based on the threshold.

According to the present applicable visual inspection management system 9 as described above, the user who performs the visual inspection as the secondary inspection of the visual inspection can refer to only the images having the feature amount close to the threshold value at a glance. Therefore, inspection of clear defects can be omitted, and a plurality of images can be confirmed on one screen, so visual inspection can be made more efficient. Furthermore, since the defect determination line indicating the threshold is displayed, it is possible to determine the defect of the image based on objective indicators. This can prevent fluctuations in determination.

<Embodiment 1> Next, the appearance inspection management system 1 which is another example of the form for implementing the present invention will be described. However, the dimensions, materials, shapes, and relative arrangements of the components described in this embodiment are not intended to limit the scope of the present invention to these unless otherwise stated.

(system structure) The overall structure of the appearance inspection management system according to the embodiment of the present invention will be described with reference to FIG. 3. FIG. 3 is a schematic diagram showing the system configuration of the appearance inspection management system 1. As shown in FIG. 3, the visual inspection management system 1 of this embodiment has the visual inspection apparatus 2 and the inspection management apparatus 3 as a main structure. (Visual inspection device) The appearance inspection device 2 is a device for acquiring an appearance image of a sheet-like article and performing defect detection based on the image. The main structure includes an illumination system, a measurement system, a conveying mechanism (not shown), and a control system. Terminal 23.

The inspection object T is transported in the horizontal direction (arrow direction) by a transport mechanism not shown. During the transport, the external appearance image of the inspection object T is continuously acquired by the measurement system, and implementation is performed based on this an examination. The inspection object T is formed in a sheet shape, and examples thereof include paper, cloth, and film. Moreover, it is not limited to a single raw material, and may be a sheet body having a plurality of layers, such as a wrapping paper formed by bonding a film and a nonwoven fabric. Moreover, foods such as dried seaweed may also be used.

The lighting system includes a light source 211 that irradiates visible light (for example, white light) to the surface of the inspection object T. For these light sources, for example, Light Emitting Diode (LED) lighting can also be used.

The measurement system includes a camera 221 that captures light irradiated from the light source 211 and reflected by the surface of the inspection object T (hereinafter referred to as surface reflection light). The camera corresponds to the photographing means in the present invention. In addition, the cameras each include a light-receiving sensor capable of detecting the captured light, a lens, and a signal output unit, and output the light detected by the light-receiving sensor through the lens as an electrical signal. As the sensor, for example, a charge coupled device (CCD) sensor or a complementary metal oxide semiconductor (Complementary Metal Oxide Semiconductor, CMOS) sensor can be used.

The camera 221 captures an image of the inspection object irradiated with the illumination light from the light source 211, and the control terminal 23 performs image processing on the captured image. The obtained feature value and the preset inspection The threshold value is compared, and the part having the characteristic amount deviating from the threshold value is determined as a defect.

The control terminal 23 has various functional modules such as an image acquisition unit 231, a feature amount calculation unit 232, a defect determination unit 233, a defect type classification unit 234, and a defect candidate extraction unit 235. Among them, functions other than the defect type classification unit 234 The modules are almost the same as those described in the application examples, so detailed descriptions are omitted.

The defect type classification unit 234 classifies the type of the defect based on a predetermined threshold value and the feature amount of the image representing the defect when a defect is detected from the inspection object by the judgment of the defect judgment unit 233. In addition, the defect candidate image extracted by the defect candidate extraction unit 235 can also be classified in the same way. The types of defects classified can be arbitrarily set by the user. For example, the types of foreign matter mixed in, stains, wrinkles, holes, etc. can be set, and they can also be further classified into sub-categories (such as insects, wood chips, metal foreign objects, oil, water, large holes, etc.) Small holes etc.).

(Inspection management device) The visual inspection device 2 is connected to the inspection management device 3 via a network (Local Area Network (LAN)), and the visual inspection device 2 and the inspection management device 3 perform two-way communication of information. The inspection management device 3 processes the information received from the visual inspection device 2 and sends information related to the inspection to the visual inspection device 2. The inspection management device 3 includes a general-purpose computer system, and the general-purpose computer system includes a CPU, a main memory device, an auxiliary memory device (all not shown), an input device 34, a display device 35, and the like.

In addition, the inspection management device 3 may include one computer or multiple computers. Alternatively, all or part of the functions of the inspection management device 3 may be installed in the control terminal 23 of the appearance inspection device 2. Alternatively, a part of the functions of the inspection management device 3 may also be implemented by a server (cloud server, etc.) on the network.

The inspection management device 3 of this embodiment includes a defect candidate image acquisition unit 31, a visual inspection support unit 32, and an inspection standard setting unit 33 as functional modules.

The defect candidate image acquisition unit 31 is a function of acquiring defect candidate images from the appearance inspection device 2. Moreover, defect candidate images can also be obtained from other places on the Internet. The visual inspection assistance unit 32 is a function for displaying a screen for assisting the visual inspection on the display device 35. The screen displayed on the display device 35 by the visual inspection assistance unit 32 will be described later. The inspection standard setting unit 33 is a function of accepting input from the user via the input device 34 and setting the types of feature quantities and their thresholds used in the visual inspection by the visual inspection device 2. In addition, the inspection standard setting unit 33 in this embodiment corresponds to the threshold value setting means and the inspection result correction means in the present invention. That is, in the visual inspection management system of the present embodiment, a configuration is adopted in which the inspection standard setting unit serves as both the threshold setting means and the inspection result correction means.

(Check the processing flow in the management system) Next, referring to FIG. 4, the flow of processing performed by the appearance inspection management system 1 in this embodiment will be described. First, in the visual inspection apparatus 2, the inspection object T is photographed, and the control terminal 23 acquires an image of the inspection object via the image acquisition unit 231 (step S101 ). Next, the feature quantity calculation unit 232 calculates the value of the predetermined feature quantity from the inspection object image (step S102), and the defect determination unit 233 and the defect type classification unit 234 compare the calculated feature quantity value with the preset value. A check is performed by comparison with the check threshold value (step S103). That is, in step 103, a determination is made regarding the presence or absence of defects and the types of defects. In addition, the determined information may also be sent to the inspection management device 3 together with the image data of the inspection object.

Next, the defect candidate extraction unit 235 compares the value of the feature value of the inspection object image calculated by the feature value calculation unit 232 with the inspection threshold value. When the value of the feature value is present relative to the inspection threshold value, When the part is within the set predetermined margin (margin), an image including the part is extracted as a defect candidate image (step S104). The extracted image is sent to the inspection management device 3 and stored in the storage device by the defect candidate image acquisition unit 31. In addition, the defect candidate image acquisition unit 31 may acquire defect candidate images every time a defect candidate image is extracted, or in a predetermined unit (for example, a roll, a lot of products, etc.). After the inspection is over, the defect candidate images of each specified unit are uniformly acquired.

Then, at the stage when the inspection of the inspection object T of the predetermined unit is completed, the visual inspection assistant 32 displays a list of the memorized defect candidate images on the display device 35 in accordance with a predetermined arrangement rule (step S105) . Furthermore, a defect determination line is also displayed together, and the defect determination line indicates an inspection threshold value, and the defect candidate images displayed in a list are divided according to whether the inspection threshold value is exceeded (step 106).

In addition, for the arrangement of the list display, for example, it is possible to perform the descending arrangement from an image with a large difference from the threshold value of the feature amount corresponding to each type of the feature amount used for inspection. Fig. 5 is a diagram showing an example of a screen in which defect candidate images are displayed in a list. The broken line in FIG. 5 represents the defect determination line. As shown in Fig. 5, based on the viewpoints of the two characteristic quantities of the brightness value peak level (the degree of deviation from the brightness value of the texture) and the area of the part exhibiting different brightness from the texture, the defect candidate images are arranged in a grid shape. Fig. 5 shows that the feature quantity of the peak level, the higher the image, the greater the degree of deviation from the texture, the feature quantity of the area, the left side of the image, and the texture has a different brightness value. The larger the area.

Furthermore, it is also possible to display the classification of the types of defects and the number of defects for each type. As shown in FIG. 5, on the right side of the defect candidate image list, a table showing the number of each defect type is displayed. The defect candidate image in the area indicated by O in the figure corresponds to the defect of defect type 1, the defect candidate image in the area indicated by P in the figure corresponds to the defect of defect type 2, and the area indicated by Q in the figure The defect candidate image of is equivalent to defect type 3 defects, and the defect candidate image in the area indicated by R in the figure corresponds to defect type 4 defects.

The inspector who performed the secondary inspection of the visual inspection performed the visual inspection of the defect candidate image while observing the screen display shown in FIG. 5. At this time, the inspector can change the inspection threshold. Specifically, when it is determined from the relationship between the list of defect candidate images and the defect determination line that the inspection threshold should be changed, an operation of relatively moving at least one of the defect determination line and the defect candidate image via the input device 34 is performed, In this way, the threshold can be changed.

Fig. 6 shows an example of a screen displaying a list of images when such an operation is performed. The broken lines shown in FIG. 6(A) and FIG. 6(B) respectively indicate defect determination lines. FIG. 6(A) shows an example of a screen when the defect candidate image is moved to the opposite side of the defect determination line indicating the threshold. On the other hand, FIG. 6(B) shows an example of a screen when the defect determination line is moved.

The description will return to the processing flow performed by the appearance inspection management system 1, and the inspection management device 3 determines whether or not the threshold value change operation has been performed via the input device 34 (step S107). Here, if no operation is performed, a series of processing is directly ended. Alternatively, it is also possible to request the user to perform an input for verifying the inspection result, and when the user inputs, the processing is ended.

On the other hand, if the threshold value change operation is performed in step S107, an attention display for reminding that there is a change is performed in the image list display (step S108). For example, as shown in Fig. 6(A) and Fig. 6(B), the display color of the defect candidate image whose defect judgment result has changed due to the threshold value change can be changed, or thick and dark can be used. The colored frame surrounds the image. Then, the inspection threshold value is changed by the inspection standard setting unit 33, and the setting is transmitted to the appearance inspection apparatus 2 (step S109), and a series of processing ends.

With the above-mentioned inspection management system, during the secondary inspection of the visual inspection, not only the visual inspection can be performed efficiently, but the inspection can be performed while comparing multiple images with their threshold lines. Correction of the threshold. This can suppress fluctuations in the threshold value change.

(Modification) In addition, the visual inspection auxiliary unit 32 can also display a screen other than the above-mentioned screen. For example, the visual inspection auxiliary unit 32 can display a feature quantity distribution map, which is a feature quantity value obtained from one or more object images as the coordinates of the coordinate system and is arranged to be specified by The feature quantity is defined in the coordinate system. FIG. 7 is an example of a feature quantity distribution map displayed on the display device 35 by the visual inspection assistance unit 32. The screen shown in Figure 7 is a project in which the peak gray scale value is set on the X axis as the feature amount, and the area is set as the feature amount on the Y axis, and the image of the inspection object with the feature amount located at each coordinate The person doing the mapping.

The dotted lines in FIG. 7 are threshold value display lines indicating the inspection threshold values of each feature amount. When the threshold value is changed by the inspection standard setting unit 33, the threshold value display line is displayed in a position that reflects the change in conjunction with this.

With such a display, it is possible to confirm at a glance the distribution of the feature amount in the image of the inspection object and the relationship with the inspection threshold. Furthermore, it is possible to study the difference area of the extracted defect candidate image while comparing the distribution of the threshold value display line and the feature amount.

＜Other＞ The above-mentioned embodiments are merely illustrative of the present invention, and the present invention is not limited to the specific forms described above. The present invention can be variously modified within the scope of its technical idea. For example, as shown in FIG. 8, the feature quantity distribution map may be displayed simultaneously with the list display of defect candidate images.

Furthermore, in each of the above-mentioned examples, the defect determination unit and the defect candidate extraction unit are described as independent functional modules, but they may be integrated. That is, when there is a part where the value of the feature amount of the inspection object image is within a predetermined margin range set with respect to the inspection threshold, the part may be determined as a defect, and the determined part may be included. The image of the defective part is extracted as a defect candidate image. At this time, in the processing flow of the first embodiment, step S103 and step S104 will be executed simultaneously.

In addition, in the above-mentioned embodiment, the apparatus for inspecting the sheet-shaped inspection object is an object, but the present invention is not limited to this, and can be widely applied to an appearance inspection apparatus that performs image processing.

A technical solution of the present invention is an appearance inspection management system, which includes: a photographing component (221), which photographs an object to be inspected; an inspection component (233), which determines from the object to be photographed by the photographing component according to a predetermined threshold The feature quantity obtained by the image is used to detect the defect of the inspected object; a defect candidate extraction part (235) extracts from the inspected object image a predetermined difference with respect to the predetermined threshold Defect candidate images with feature values within the range; a display part (35); and a visual inspection auxiliary part (32) on which the image list display and the defect determination line are displayed, and the image list display is One or more of the defect candidate images are arranged according to the value of the feature value of each image, the defect determination line indicates the threshold value, and all the defects are classified according to whether the threshold value is determined as a defect. Defect candidate images in the image list display.

Moreover, another technical solution of the present invention is a visual inspection management method that manages the visual inspection of an inspected object. The visual inspection management method includes: a photographing step (S101), photographing the inspected object; and a defect candidate extraction step ( S104) Extract a defect candidate image, the defect candidate image is the feature amount obtained from the image of the inspection object taken in the photographing step and converges within a predetermined difference range with respect to a predetermined threshold Image; and visual inspection auxiliary steps (S105, S106), the image list display and defect determination line are displayed on the same screen, the image list display is based on the value of the feature value of each image One or more defect candidate images extracted in the defect candidate extraction step are arranged, and the defect determination line represents the threshold value, and the defect determination line is determined to be a defect based on the relationship with the threshold value. Defect candidate images in the image list display.

1, 9: Appearance inspection management system 2.91: Visual inspection device 3.92: Inspection management device 23, 913: control terminal 31, 921, 9134: Defect candidate image acquisition department 32, 922: Visual inspection auxiliary department 33: Inspection standard setting section 34: input device 35: display device 93: display parts 211, 912: light source 221, 911: Camera 231, 9131: Image acquisition department 232, 9132: Feature calculation unit 233, 9133: Defect Judgment Department 234: Defect Type Classification Department 235: Defect Candidate Extraction Department S101~S109: steps T: Inspection object

FIG. 1 is a schematic diagram showing the structure of an appearance inspection management system of an application example of the present invention. Fig. 2 is a diagram showing an example of a screen displayed on a display member by a visual inspection support unit of an application example. Fig. 3 is a schematic diagram showing the structure of an appearance inspection management system according to an embodiment. 4 is a flowchart showing the flow of processing of the appearance inspection management system of the embodiment. Fig. 5 is a first diagram showing an example of a screen displayed on the display device by the visual inspection support unit of the embodiment. FIG. 6(A) is a second diagram showing an example of a screen displayed on the display device by the visual inspection support unit according to the embodiment. FIG. 6(B) is a third diagram showing an example of a screen displayed on the display device by the visual inspection support unit according to the embodiment. Fig. 7 is a fourth diagram showing an example of a screen displayed on the display device by the visual inspection support unit of the embodiment. Fig. 8 is a fifth diagram showing an example of a screen displayed on the display device by the visual inspection support unit of the embodiment.

1: Appearance inspection management system

2: Visual inspection device

3: Check the management device

23: Control terminal

31: Defect Candidate Image Acquisition Department

32: Visual inspection auxiliary department

33: Inspection standard setting section

34: input device

35: display device

211: light source

221: Camera

231: Image Acquisition Department

232: Feature calculation unit

233: Defect Judgment Department

234: Defect Type Classification Department

235: Defect Candidate Extraction Department

T: Inspection object

Claims (15)

An appearance inspection management system, including: Shooting parts, shooting the inspected object; An inspection component, comparing the feature amount obtained from the image of the inspected object taken by the imaging component with a prescribed threshold, thereby making a determination to detect the defect of the inspected object; A defect candidate extracting means extracting, from the inspection object image, a defect candidate image having a feature value within a predetermined difference range with respect to the predetermined threshold; Display parts; and A visual inspection auxiliary component that displays a list of images and a defect determination line on the display component, and the list of images displays one or more of the defect candidate images based on the value of the feature value of each image Arranged, the defect determination line indicates the threshold, and the defect candidate images in the image list display are classified according to whether they are determined to be defects according to the threshold. The appearance inspection management system according to claim 1, wherein There are multiple thresholds, The visual inspection auxiliary component displays the defect determination line corresponding to the number of the threshold value. The appearance inspection management system as described in claim 1 or 2, wherein The inspection component acquires a variety of feature quantities from the image of the object to be inspected, and detects defects of the object to be inspected based on a threshold corresponding to each feature quantity. The appearance inspection management system according to claim 3, wherein The image list display is formed by arranging one or more defect candidate images according to the value of the feature amount of each image corresponding to each type of feature amount. The appearance inspection management system as described in claim 1 or claim 2, further including: The defect type classification component classifies the type of the defect when a defect is detected from the inspection object. The appearance inspection management system according to claim 5, wherein The visual inspection auxiliary component corresponds to each type of defects classified by the defect type classification component, and the number of the defects is displayed on the display component. The appearance inspection management system as described in claim 1, further including: Input parts; and The inspection result correction means receives an operation of relatively moving the defect determination line and at least one of the defect candidate images in the image list display via the input means. The appearance inspection management system according to claim 7, wherein The inspection result correction unit is used for the attention display of the defect candidate image that has moved to the opposite side of the defect determination line compared to before the operation by the operation, and is displayed on the display unit . The appearance inspection management system according to claim 7 or 8, wherein The inspection result correction means accepts an operation of relatively moving the defect determination line and at least one of the defect candidate images in the image list display, thereby setting and/or changing the predetermined threshold. The appearance inspection management system as described in claim 1 or 2, wherein The visual inspection auxiliary component displays a feature quantity distribution map and the image list display simultaneously or switchably on the display component in a coordinate system defined by a predetermined feature quantity, the feature quantity distribution diagram The feature value obtained from one or more images of the inspection object is arranged as the coordinates of the coordinate system. The appearance inspection management system described in claim 10 further includes: Threshold setting means to set and/or change the prescribed threshold, Displaying a threshold value display line indicating the prescribed threshold value on the feature quantity distribution graph, When the predetermined threshold value is changed by the threshold value setting means, the change of the threshold value is reflected in the display of the threshold value display line. An appearance inspection management device, which at least includes the visual inspection auxiliary component, The appearance inspection management device constitutes at least a part of the appearance inspection management system according to any one of claim 1 to claim 11. An appearance inspection management system, including: Transport parts, continuous transport of sheet-shaped objects to be inspected; A photographing component, continuously photographing the inspected object in transport; An inspection component, comparing the feature amount obtained from the image of the inspected object taken by the imaging component with a predetermined threshold, thereby making a determination to detect the defective part of the inspected object; Defect candidate extraction means extracting, from the inspection object image, an image having a feature value within a predetermined difference range from the predetermined threshold, that is, a defect candidate image; Display parts; and A visual inspection auxiliary component that displays a list of images and a defect determination line on the display component, and the list of images displays one or more of the defect candidate images based on the value of the feature value of each image Arranged, the defect determination line indicates the threshold, and the defect candidate images in the image list display are classified according to whether they are determined to be defects according to the threshold. A visual inspection management method, which manages the visual inspection of an inspected object, the visual inspection management method includes: Shooting steps, shooting the inspected object; The defect candidate extraction step extracts a defect candidate image, the defect candidate image being the feature amount obtained from the image of the inspection object captured in the imaging step and converges within a predetermined difference range with respect to a predetermined threshold Images within; and The visual inspection auxiliary step is to display the image list display and the defect determination line on the same screen, and the image list display is based on the value of the feature amount of each image to extract the defect candidate extraction step One or more of the defect candidate images are arranged, the defect determination line indicates the threshold value, and the defect candidate images in the image list display are determined as a defect based on the relationship with the threshold value To divide. A program for making the information processing device execute the steps described in claim 14.

Images